Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    data loss/security

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    偷
    -0.07
     snake
    -0.06
    包括
    -0.06
    -0.06
     Spar
    -0.06
     narrowly
    -0.06
    EDGE
    -0.06
    .PNG
    -0.06
     intellig
    -0.06
    انا
    -0.06
    POSITIVE LOGITS
     Threshold
    0.07
    тен
    0.07
    人民政府
    0.07
    бел
    0.07
    老年
    0.06
    VERTISEMENT
    0.06
    izr
    0.06
    azu
    0.06
    ournaments
    0.06
    隩
    0.06
    Act Density 0.013%

    No Known Activations